Layer 19 · Neuron 8525 · boosted

L19N8525+1

Word quirks:

“代表”“ representing”“ representative”“代表的”“ represents”“represent”“代表了”“代表着”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen, the large-scale model for AI. I am designed to answer questions on various fields, create content for different scenarios, and assist with daily tasks. My mission is to provide high-quality responses that meet user needs, whether they are related to knowledge, creativity, or problem-solving. I strive to be a helpful assistant for individuals and organizations by delivering accurate, efficient, and reliable information. Let me know how I can help!

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L21N4555-1🕒	1.00	“代表”“ representing”“代表的”
2. L16N7823+1💥	0.99	“代表了”“代表”“ represents”
3. L22N5896+1🕒	0.99	“代表”“ represents”“代表的”
4. L20N7726+1🕒	0.99	“ representing”“代表”“ represent”
5. L24N1310+1💤	0.99	“代表”“代表了”“ representing”
6. L17N6909-1🕒	0.99	“ representing”“代表”“ representation”
7. L14N5566+1🕒	0.99	“ represents”“ representing”“ representative”
8. L19N5825+1💤	0.98	“代表”“代表的”“ represent”
9. L24N7708-1🕒	0.97	“代表”“ represent”“ representing”
10. L22N3346-1💤	0.97	“ representing”“ represents”“代表”

Shadow specimen, apart from the ten: L19N8525-1💤, 0.18.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 19, neuron 8525, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.81, top-1 agreement 0.68) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L19N8525+1 t0-v0.1	0.811	0.68	0.963	1.24	Top boosted tokens ↑
L19N8525-1💤 shadow specimen t0-v0.1	0.576	0.73	0.713	1.23	“ to”“to”“ để”“ щоб”“关于”“来确定”“ щодо”“để”

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.